Exploring Deep Recurrent Q-Learning for Navigation in a 3D Environment

Brejl, Rasmus Kongsmar and Purwins, Henrik and Schoenau-Fog, Henrik (2018) Exploring Deep Recurrent Q-Learning for Navigation in a 3D Environment. EAI Endorsed Transactions on Creative Technologies.

[thumbnail of 25776.pdf] PDF
25776.pdf
Download (1MB)

Abstract

Learning to navigate in 3D environments from raw sensory input is an important step towards bridging the gap between human players and artificial intelligence in digital games. Recent advances in deep reinforcement learning have seen success in teaching agents to play Atari 2600 games from raw pixel

Item Type: Article
Date Deposited: 04 Mar 2026 11:07
Last Modified: 12 Apr 2026 08:08
URI: http://eprints.eai.eu/id/eprint/17102

Actions (login required)

View Item
View Item